Skip to main content
POST
/
sound_clone
/
api
/
v1
/
tts
/
stream
curl --location 'https://api.myvocal.ai/sound_clone/api/v1/tts/stream' \
--header 'accessKey: <your_api_key>' \
--header 'Content-Type: application/json' \
--data '{
  "voiceId": "<voice_id>",
  "title": "tts-stream-default",
  "text": "Hello from MyVocal streaming endpoint.",
  "language": "en",
  "voiceSettings": {
    "stability": 0.7
  }
}' \
--output output-default.mp3

audio/mpeg stream (binary)

Documentation Index

Fetch the complete documentation index at: https://wiz-myvocal.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

​
accessKey
string
required
API key for authentication.

​
Body

​
voiceId
string
required
Voice ID returned by GET /sound_clone/api/v1/voices.
​
title
string
Optional title for the generated record.
​
text
string
required
Text to synthesize.
​
language
string
Language selector.
Default/V2 path: required and must use existing mapped language values.
myvocal_v3: optional. If provided, it is forwarded to upstream as language. If omitted, upstream auto-detect is used.
See supported V3 codes in V3 Language Codes (98 languages).
​
modelId
string
Optional explicit model selector.
Omit it to use the default model path.
Set myvocal_v3 to request the V3 path.
​
voiceSettings
object
For advanced settings, use suggested values unless you have strong tuning needs.
For myvocal_v3, the currently publicly documented stability values are:
- 0.5: natural pronunciation, closer to normal human speech.
- 1: more stable output with less variation.

​
Prompt Control (myvocal_v3)

Reference capability source: v3.myvocal.ai. Use [tag] in text to guide style and delivery.
Basic syntax: 
[tag] Your text content
Examples: 
[happy] Hello everyone, welcome to MyVocal.
[laughter] That was funny.
Representative categories:
  • Emotion control: happy, excited, sad, angry, surprised
  • Non-speech sounds: laughter, throat clearing, yawning, shushing, screaming
  • Sound-related effects: breathing, sighing, gasping, crying, murmuring

​
Response

​
Content-Type
string
Success usually returns audio/mpeg.
​
Body
stream
Binary audio stream payload.
curl --location 'https://api.myvocal.ai/sound_clone/api/v1/tts/stream' \
--header 'accessKey: <your_api_key>' \
--header 'Content-Type: application/json' \
--data '{
  "voiceId": "<voice_id>",
  "title": "tts-stream-default",
  "text": "Hello from MyVocal streaming endpoint.",
  "language": "en",
  "voiceSettings": {
    "stability": 0.7
  }
}' \
--output output-default.mp3

audio/mpeg stream (binary)

​
Common errors

  • Invalid language option.: non-V3/default path is missing or using an unsupported language value.
  • VOICE_NOT_FOUND: voiceId is invalid or not available under this API key.
  • code = -1: upstream or backend failed to complete generation.